Physics Informed Neural Networks
A Physics Informed Neural Network predicts the two-dimensional viscous flow field of the flow past a cylinder rotating at a constant rate of rotation in an incompressible flow. The flow is numerically simulated using an open source CFD software tool, OpenFOAM.
The PINN model in this project is trained to obey the governing Navier-Stokes equations as a penalising regularisation loss using automatic differentiation in the open source machine learning software tool TensorFlow in which the PINN is developed. The PINN is also shown to have better performance than a neural network (NN) which is not physics based but trained with CFD Data, especially with scarce data. Note that the Code is proprietary and confidential.